# Generation of Synthetic Images for Pedestrian Detection Using a Sequence of GANs

arXiv: https://arxiv.org/abs/2401.07370 · HTML: https://mlsanity.com/paper/2401.07370/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 14 Jan 2024.

## Builds on (most cited first, 28 of 28)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Self-Normalizing Neural Networks](https://mlsanity.com/paper/1706.02515/) (2017)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [Virtual Worlds as Proxy for Multi-Object Tracking Analysis](https://mlsanity.com/paper/1605.06457/) (2016)
- [Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization](https://mlsanity.com/paper/1804.06516/) (2018)
- [Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?](https://mlsanity.com/paper/1610.01983/) (2016)
- [Playing for Benchmarks](https://mlsanity.com/paper/1709.07322/) (2017)
- [Enhancing Photorealism Enhancement](https://mlsanity.com/paper/2105.04619/) (2021)
- [Multimodal Deep Learning for Robust RGB-D Object Recognition](https://mlsanity.com/paper/1507.06821/) (2015)
- [Effective Use of Synthetic Data for Urban Scene Semantic Segmentation](https://mlsanity.com/paper/1807.06132/) (2018)
- [Context-Aware Synthesis and Placement of Object Instances](https://mlsanity.com/paper/1812.02350/) (2018)
- [Mixing Real and Synthetic Data to Enhance Neural Network Training -- A Review of Current Approaches](https://mlsanity.com/paper/2007.08781/) (2020)
- [PeopleSansPeople: A Synthetic Data Generator for Human-Centric Computer Vision](https://mlsanity.com/paper/2112.09290/) (2021)
- [High-resolution Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1711.06491/) (2017)
- [Adversarial Pixel-Level Generation of Semantic Images](https://mlsanity.com/paper/1906.12195/) (2019)

## Abstract (arXiv)

Creating annotated datasets demands a substantial amount of manual effort. In this proof-of-concept work, we address this issue by proposing a novel image generation pipeline. The pipeline consists of three distinct generative adversarial networks (previously published), combined in a novel way to augment a dataset for pedestrian detection. Despite the fact that the generated images are not always visually pleasant to the human eye, our detection benchmark reveals that the results substantially surpass the baseline. The presented proof-of-concept work was done in 2020 and is now published as a technical report after a three years retention period.